OpenClaw Is Now Available on NEAR AI Cloud

OpenClaw—previously known as OpenClaw and Clawdbot—has taken the AI world by storm. Created by Peter Steinberger, OpenClaw is an open-source personal agent framework that has become one of the fastest-growing repositories in GitHub history, with over 60,000+ stars and a global community eagerly building always-on personal AI assistants.

The appeal is obvious: OpenClaw actually does things. It connects to your Gmail, calendar, and Notion. It remembers context across conversations. It runs 24/7, handling everything from inbox management to flight check-ins. You chat with it over Telegram or WhatsApp. It’s less like a chatbot and more like a tireless coworker.

The Catch

To be useful, OpenClaw needs deep, persistent, full system access. It reads your email. It stores your API keys. It builds an evolving model of your habits and preferences over time. That’s what makes it powerful, but also very risky to deploy.

Today, you must typically choose between two options:

• • Local hardware: Buy a Mac Mini ($600). Expensive, brittle, and forces you to become a sysadmin.

• • Standard cloud VMs: Deploy on AWS EC2 ($5-20/mo). Convenient,  but exposes your most sensitive data—credentials, memory, and context—to cloud-level security risks and trust assumptions.

Neither option is ideal for long-running agents that need both autonomy and strong security guarantees.

A Third Option: OpenClaw in a Trusted Execution Environment

Today, we’re launching OpenClaw hosting on NEAR AI Cloud, running inside Trusted Execution Environments (TEEs).

A TEE is a secure enclave where code and data are protected from everything outside it, including the operating system and the cloud provider itself. Your OpenClaw runs in an encrypted execution environment that no external party can inspect, including NEAR AI.

This is not “we promise not to look” privacy. It’s cryptographic by design:

• • Hardware-level memory encryption

• • Cryptographic attestation of what code is running

• • Provider-blind execution—NEAR AI cannot inspect your workload

This means long-term memory, credentials, and tool access can persist without ever leaving encrypted memory—even while running in the cloud. 

You get cloud convenience with security guarantees that ad hoc local hardware in your closet or standard VPS deployments cannot match.

Built for Agent Workloads, Not Just Inference

Unlike generic confidential VMs designed for short-lived inference jobs, NEAR AI Cloud is purpose-built for agent workloads: long-running processes, persistent state, and secure access to real-world tools.

NEAR AI Cloud already supports confidential AI workloads used in sensitive enterprise contexts. OpenClaw is a natural extension of that capability, bringing cryptographic privacy guarantees to personal and autonomous agents.

Hosting OpenClaw on NEAR AI Cloud is a concrete example of NEAR’s core thesis in action: confidential, verifiable AI that developers can trust with real autonomy.

No Hardware. No Data Exposure.

We’re keeping it simple:

1. 1. Create a NEAR AI Cloud account

1. 1. Request access to the OpenClaw beta

1. 1. Once approved, Deploy OpenClaw into a private TEE instance

1. 1. Authenticate via the OpenClaw CLI and begin running your agent

OpenClaw’s CLI handles configuration. NEAR AI Cloud handles the secure infrastructure.

Get Early Access

OpenClaw hosting on NEAR AI Cloud is available now to a limited group of beta users. Beta users can subscribe using NEAR tokens or standard debit and credit cards.  

If you’ve been waiting to try OpenClaw because you didn’t want to manage dedicated hardware or didn’t trust a standard cloud VM with your agent’s memory and credentials, this is your moment.

Get early access to OpenClaw on NEAR AI Cloud→